AbstractBackgroundDeep learning (DL) of non‐invasive brain structural magnetic resonance imaging (sMRI) has shown superb performance in differentiating Alzheimer’s disease (AD) from cognitively healthy participants (HC). Attention is needed to tackle AD pathological progression on sMRI using interpretable DL methods. Here, we studied the feasibility of DL in identifying neurodegenerative progression patterns in AD.MethodData applied to the study were from the multi‐centre Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) with 2,369 T1‐weighted brain images of 1,005 subjects. An interpretable DL technique named the ensemble 3‐dimensional convolutional neural network (Ensemble 3DCNN) was used to detect the longitudinal trajectory of sMRI changes during AD progression. The model used multiple 3D convolutional neural networks and a meta‐classifier to assess the degree of brain changes through generating an index score, named P‐score. The score was derived as the outcome of training and verifying the Ensemble 3DCNN model for difference in the whole‐brain sMRI between AD and HC. The predictive P‐scores values were used to analyze the sMRI images for mining neurodegenerative brain regions. In addition, dementia stages, and the temporal and spatial connectivity patterns of neurodegeneration progression were also analyzed.ResultBrain regions showing high P‐scores (> 0.73/1.00) included the amygdala, nucleus accumbens, agranular insular cortex, and the hippocampus, matching the isocortex, basal magnocellular complex, and transentorhinal regions identified in Braak staging. The P‐score increased over time in 82% of the degenerative brain regions. The impaired areas were often spatially connected, consistently across multiple time points in the progression of AD. The trajectory of regional brain changes displayed multiple patterns with complex individual variability.ConclusionThe interpretable 3D DL model demonstrated featured deteriorations on the AD sMRI images. The finding confirmed the neuropathological degeneration of AD and captured additional whole‐brain changes, especially, relating to the heterogeneity of AD expression.